Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects Journal Article
| Authors: | Muhammad, H.; Fuchs, T. J.; De Cuir, N.; De Moraes, C. G.; Blumberg, D. M.; Liebmann, J. M.; Ritch, R.; Hood, D. C. |
| Article Title: | Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects |
| Abstract: | Purpose: Existing summary statistics based upon optical coherence tomographic (OCT) scans and/or visual fields (VFs) are suboptimal for distinguishing between healthy and glaucomatous eyes in the clinic. This study evaluates the extent to which a hybrid deep learning method (HDLM), combined with a single wide-field OCT protocol, can distinguish eyes previously classified as either healthy suspects or mild glaucoma. Methods: In total, 102 eyes from 102 patients, with or suspected open-angle glaucoma, had previously been classified by 2 glaucoma experts as either glaucomatous (57 eyes) or healthy/suspects (45 eyes). The HDLM had access only to information from a single, wide-field (9×12 mm) swept-source OCT scan per patient. Convolutional neural networks were used to extract rich features from maps derived from these scans. Random forest classifier was used to train a model based on these features to predict the existence of glaucomatous damage. The algorithm was compared against traditional OCT and VF metrics. Results: The accuracy of the HDLM ranged from 63.7% to 93.1% depending upon the input map. The retinal nerve fiber layer probability map had the best accuracy (93.1%), with 4 false positives, and 3 false negatives. In comparison, the accuracy of the OCT and 24-2 and 10-2 VF metrics ranged from 66.7% to 87.3%. The OCT quadrants analysis had the best accuracy (87.3%) of the metrics, with 4 false positives and 9 false negatives. Conclusions: The HDLM protocol outperforms standard OCT and VF clinical metrics in distinguishing healthy suspect eyes from eyes with early glaucoma. It should be possible to further improve this algorithm and with improvement it might be useful for screening. © 2017 Wolters Kluwer Health, Inc. All rights reserved. |
| Keywords: | controlled study; major clinical study; disease classification; pathophysiology; reproducibility; reproducibility of results; classification; pathology; physiology; false negative result; disease severity; access to information; algorithm; nerve fiber; detection; intraocular pressure; diagnostic test; image processing; false positive result; nerve cell network; medical expert; receiver operating characteristic; retina ganglion cell; retinal ganglion cells; optical coherence tomography; artificial neural network; neural networks (computer); diagnostic test accuracy study; nerve fibers; classifier; procedures; machine learning; visual field; intraocular hypertension; tomography, optical coherence; humans; human; priority journal; article; visual fields; random forest; gonioscopy; hybrid deep learning method; open angle glaucoma; retinal nerve fiber layer thickness; single wide field optical coherence tomography; glaucoma, open-angle; ocular hypertension |
| Journal Title: | Journal of Glaucoma |
| Volume: | 26 |
| Issue: | 12 |
| ISSN: | 1057-0829 |
| Publisher: | Lippincott Williams & Wilkins |
| Date Published: | 2017-12-01 |
| Start Page: | 1086 |
| End Page: | 1094 |
| Language: | English |
| DOI: | 10.1097/ijg.0000000000000765 |
| PUBMED: | 29045329 |
| PROVIDER: | scopus |
| PMCID: | PMC5716847 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 2 January 2018 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work